Seamless M4T v2 Large (speech → text)
facebook logo

Seamless M4T v2 Large (speech → text) · FP32 · by facebook

facebook/seamless-m4t-v2-large

facebook · FP32 · on speech-hf · vendor build

Measured by one node on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 3 Nov 2026 · every field verified against the signature of the node that produced it, and re-verifiable by you: each signed figure carries the exact bytes the node signed (signing_payload_b64) and the signature over them, and the ed25519 public key is embedded in node_did. effective_ctx is the context length a node PROVED by recall, never the length a model card advertises
context declarednot declaredwhat the runtime reported. A node attests it was told this; nobody attests it is true.
context proved by recallnot probedthe largest size at which a machine could still find tokens planted across the whole prompt — start, middle and end, all of which had to come back.
Both numbers are needed to state a gap, and one of them is missing.

Languages, proved

AssameseBengaliEnglishGujaratiKannadaMalayalamMarathiNepaliOdiaPunjabiTamilTeluguUrdu

Each question was put entirely in its own language and script, and the answer had to be right. A model with no coverage cannot parse the question, so answering in English is a failure here, not a pass. 13 proved of 14 asked — a language absent from the probe set was never asked, and is not a claim either way.

what it produced, measured

speech recognition
produced12stook2.0sspeed5.8× faster than realtime

measured on Linux, 12 cores, 53 GB · realtime_factor 0.17 (wall ÷ media)

The fastest measurement any machine reported, signed by the machine that took it. Every other machine’s numbers are in the table below — a rate is a fact about a model and a computer, and two machines disagreeing is two hardware classes rather than one of them being wrong.

Capabilities, measured

Speech inpassed
Whether the model itself accepts audio in a turn — distinct from this gram running a separate transcription engine. Recorded as unmeasured until an engine exposes the path, never as a failure.
signed by this network

What machines here proved

best throughput5.8× faster than realtime
resident while loaded6.5 GiB · did:epn:002408…dae679
machines that measured it1
regions it was proved in1
Every line traces to a node signature.
from the public record · unsigned

What the runtime says about it

No runtime metadata was attested for this model.The only unsigned block on this page. We attest we read these from the runtime — not that they are true. Nobody signs a model card.

Proven across regions

Singapore, Central Singapore190464 · 1 node

Measured by

ranked on the provider standings

The machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…dae679Singapore · 190464 · speech-hf · 3 Nov 2026Intel Xeon @ 2.20GHz · L4 22 GiB · 6 cores · 53.0 GiB RAM
✓ Speech in · 5.8× faster than realtimeprobe 8iglHGozbz…
✓ Speech in✓ 13 languages

Run this where your data already is

Tell us the workload, whose machines it should run on, and which jurisdiction it answers to.

Run a gramPut a machine on the network in this region; it signs its capacity into the room.Open a gramxStart your own room — an org, a community, a brand.Be invitedAccept a link from an admin to cross into the private room.